Skip to content

Actions: ngxson/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
332 workflow runs
332 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
metal : fix event synchronization (#22260) Check Pre-Tokenizer Hashes #385: Commit 8635e22 pushed by ngxson
12m 27s master
master
12m 27s
mtmd, llama : Update HunyuanVL vision-language model support (#22037) Check Pre-Tokenizer Hashes #384: Commit 7bfe60f pushed by ngxson
10m 26s master
master
10m 26s
auto Check Pre-Tokenizer Hashes #383: Commit 081e8fd pushed by ngxson
16m 45s xsn/model_def_self_contained
xsn/model_def_self_contained
16m 45s
convert : support sentence-transformer 5.4 config files (#22087) Check Pre-Tokenizer Hashes #382: Commit 8685e7b pushed by ngxson
10m 6s master
master
10m 6s
auto Check Pre-Tokenizer Hashes #381: Commit a8282e3 pushed by ngxson
1m 3s xsn/model_def_self_contained
xsn/model_def_self_contained
1m 3s
ggml-backend-meta: add multi-segment read support in get_tensor (#22063) Check Pre-Tokenizer Hashes #380: Commit 59accc8 pushed by ngxson
3m 12s master
master
3m 12s
fix merge Check Pre-Tokenizer Hashes #379: Commit 8c39fc8 pushed by ngxson
16m 54s xsn/one_llm_build_per_arch
xsn/one_llm_build_per_arch
16m 54s
Merge branch 'master' into xsn/model_def_self_contained Check Pre-Tokenizer Hashes #378: Commit 2c91880 pushed by ngxson
1m 22s xsn/model_def_self_contained
xsn/model_def_self_contained
1m 22s
codeowners: add team member comments (#21714) Check Pre-Tokenizer Hashes #377: Commit b572d1e pushed by ngxson
57s master
master
57s
wip HY-embodied Check Pre-Tokenizer Hashes #376: Commit 1321223 pushed by ngxson
1m 7s xsn/hy_embodied
xsn/hy_embodied
1m 7s
(WIP) falcon-ocr, for discussion Check Pre-Tokenizer Hashes #375: Pull request #100 opened by ngxson
1m 22s xsn/falcon-ocr
xsn/falcon-ocr
1m 22s
wip Check Pre-Tokenizer Hashes #374: Commit e85f231 pushed by ngxson
1m 6s xsn/falcon-ocr
xsn/falcon-ocr
1m 6s
wip, rope to be added Check Pre-Tokenizer Hashes #373: Commit c6b9d67 pushed by ngxson
55s xsn/falcon-ocr
xsn/falcon-ocr
55s
wip model load Check Pre-Tokenizer Hashes #372: Commit b8e84f6 pushed by ngxson
57s xsn/falcon-ocr
xsn/falcon-ocr
57s
add mtmd impl Check Pre-Tokenizer Hashes #371: Commit 4a5cb80 pushed by ngxson
1m 16s xsn/falcon-ocr
xsn/falcon-ocr
1m 16s
initial support for conversion script Check Pre-Tokenizer Hashes #370: Commit 000876c pushed by ngxson
1m 30s xsn/falcon-ocr
xsn/falcon-ocr
1m 30s
initial support for conversion script Check Pre-Tokenizer Hashes #369: Commit ec1c4ca pushed by ngxson
1m 9s xsn/falcon-ocr
xsn/falcon-ocr
1m 9s
initial support for conversion script Check Pre-Tokenizer Hashes #368: Commit 362846e pushed by ngxson
58s xsn/falcon-ocr
xsn/falcon-ocr
58s
mtmd: qwen3 audio support (qwen3-omni and qwen3-asr) (#19441) Check Pre-Tokenizer Hashes #367: Commit 21a4933 pushed by ngxson
1h 10m 12s master
master
1h 10m 12s
convert : force f16 or f32 on step3-vl conv weights (#21646) Check Pre-Tokenizer Hashes #366: Commit 1e9d771 pushed by ngxson
19m 36s master
master
19m 36s
mtmd: use causal attn for gemma 4 audio Check Pre-Tokenizer Hashes #365: Commit 8895606 pushed by ngxson
20m 38s xsn/g4_causal_audio
xsn/g4_causal_audio
20m 38s
[Mirror] New quantization type: Q3_HIFI Check Pre-Tokenizer Hashes #364: Pull request #65 synchronize by geoffmunn
Action required geoffmunn:master
geoffmunn:master
Action required
convert : force f16 or f32 on step3-vl conv weights (#21646) Check Pre-Tokenizer Hashes #363: Commit 1e9d771 pushed by ngxson
1m 2s master
master
1m 2s
fix multi inheritance Check Pre-Tokenizer Hashes #362: Commit 8fc8698 pushed by ngxson
1m 9s xsn/qwen3a
xsn/qwen3a
1m 9s
fix bad merge Check Pre-Tokenizer Hashes #361: Commit 53d149b pushed by ngxson
1m 23s xsn/qwen3a
xsn/qwen3a
1m 23s